Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

spec : add DFlash support (#22105)

Browse Source 
* spec: add DFlash v2 support

* dflash: support sliding window attention per layer_types

* docs: add dflash section

---------

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
This commit is contained in:
Ruixiang Wang
2026-06-28 16:01:34 +03:00
committed by GitHub
co-authored by Kashif Rasul
parent c1a1c8ee94
commit d1b34251bc
14 changed files with 712 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/models.h
+16
View File
@@ -1122,6 +1122,22 @@ struct llama_model_eagle3 : public llama_model_base {
};
struct llama_model_dflash : public llama_model_base {
llama_model_dflash(const struct llama_model_params & params) : llama_model_base(params) {}
void load_arch_hparams(llama_model_loader & ml) override;
void load_arch_tensors(llama_model_loader & ml) override;
template <bool is_enc>
struct graph : public llm_graph_context {
graph(const llama_model & model, const llm_graph_params & params);
ggml_tensor * build_inp_embd_enc() const;
};
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
};
struct llama_model_mistral4 : public llama_model_deepseek2 {
llama_model_mistral4(const struct llama_model_params & params) : llama_model_deepseek2(params) {}
// reuse load_arch_hparams and load_arch_tensors from llama_model_deepseek2